{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,11]],"date-time":"2026-09-11T22:27:51Z","timestamp":1789165671240,"version":"build-2803163510"},"publisher-location":"Cham","reference-count":57,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032370945","type":"print"},{"value":"9783032370952","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026]]},"DOI":"10.1007\/978-3-032-37095-2_6","type":"book-chapter","created":{"date-parts":[[2026,9,8]],"date-time":"2026-09-08T07:04:38Z","timestamp":1788851078000},"page":"92-110","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["OmniHuman: A Large-Scale Dataset and\u00a0Benchmark for\u00a0Human-Centric Video Generation"],"prefix":"10.1007","author":[{"given":"Lei","family":"Zhu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xing","family":"Cai","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yingjie","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yiheng","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Binxin","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hao","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jie","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chen","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jing","family":"Lyu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,9]]},"reference":[{"key":"6_CR1","unstructured":"An, K., et\u00a0al.: FunAudioLLM: voice understanding and generation foundation models for natural interaction between humans and LLMs. arXiv preprint arXiv:2407.04051 (2024)"},{"key":"6_CR2","unstructured":"An, K., et al.: Fun-ASR technical report (2025). https:\/\/arxiv.org\/abs\/2509.12508"},{"key":"6_CR3","doi-asserted-by":"crossref","unstructured":"Caba Heilbron, F., Escorcia, V., Ghanem, B., Carlos Niebles, J.: ActivityNet: a large-scale video benchmark for human activity understanding. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 961\u2013970 (2015)","DOI":"10.1109\/CVPR.2015.7298698"},{"key":"6_CR4","doi-asserted-by":"crossref","unstructured":"Chen, Y., et\u00a0al.: 3D-speaker-toolkit: an open-source toolkit for multimodal speaker verification and diarization. In: ICASSP 2025-2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp.\u00a01\u20135. IEEE (2025)","DOI":"10.1109\/ICASSP49660.2025.10888389"},{"key":"6_CR5","unstructured":"Chen, Y., et al.: Hunyuanvideo-avatar: high-fidelity audio-driven human animation for multiple characters. arXiv preprint arXiv:2505.20156 (2025)"},{"key":"6_CR6","doi-asserted-by":"crossref","unstructured":"Chen, Z., et al.: MoVa: towards generalizable classification of human morals and values. In: Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, pp. 33204\u201333248 (2025)","DOI":"10.18653\/v1\/2025.emnlp-main.1687"},{"key":"6_CR7","doi-asserted-by":"crossref","unstructured":"Chung, J.S., Nagrani, A., Zisserman, A.: VoxCeleb2: deep speaker recognition. arXiv preprint arXiv:1806.05622 (2018)","DOI":"10.21437\/Interspeech.2018-1929"},{"key":"6_CR8","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"251","DOI":"10.1007\/978-3-319-54427-4_19","volume-title":"Computer Vision \u2013 ACCV 2016 Workshops","author":"JS Chung","year":"2017","unstructured":"Chung, J.S., Zisserman, A.: Out of time: automated lip sync in the wild. In: Chen, C.-S., Lu, J., Ma, K.-K. (eds.) ACCV 2016. LNCS, vol. 10117, pp. 251\u2013263. Springer, Cham (2017). https:\/\/doi.org\/10.1007\/978-3-319-54427-4_19"},{"key":"6_CR9","unstructured":"D\u00e9fossez, A., Usunier, N., Bottou, L., Bach, F.: Demucs: deep extractor for music sources with extra unlabeled data remixed. arXiv preprint arXiv:1909.01174 (2019)"},{"key":"6_CR10","doi-asserted-by":"crossref","unstructured":"Deng, J., Guo, J., Xue, N., Zafeiriou, S.: ArcFace: additive angular margin loss for deep face recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4690\u20134699 (2019)","DOI":"10.1109\/CVPR.2019.00482"},{"key":"6_CR11","unstructured":"Di\u00a0Chang, Y.S., et al.: MagicDance: realistic human dance video generation with motions & facial expressions transfer. arXiv preprint arXiv:2311.12052 (2023). 2(3), 4"},{"key":"6_CR12","unstructured":"Ding, Y., et\u00a0al.: Kling-avatar: grounding multimodal instructions for cascaded long-duration avatar animation synthesis. arXiv preprint arXiv:2509.09595 (2025)"},{"key":"6_CR13","unstructured":"Gan, Q., Yang, R., Zhu, J., Xue, S., Hoi, S.: OmniAvatar: efficient audio-driven avatar video generation with adaptive body animation. arXiv preprint arXiv:2506.18866 (2025)"},{"key":"6_CR14","unstructured":"Google DeepMind: Veo 3 (2025). https:\/\/deepmind.google\/models\/veo\/. Accessed 17 Feb 2026"},{"key":"6_CR15","unstructured":"HaCohen, Y., et al.: LTX-2: efficient joint audio-visual foundation model (2026). https:\/\/arxiv.org\/abs\/2601.03233"},{"key":"6_CR16","doi-asserted-by":"crossref","unstructured":"Hidayatullah, P., Syakrani, N., Sholahuddin, M.R., Gelar, T., Tubagus, R.: YOLOv8 to YOLO11: a comprehensive architecture in-depth comparative review. arXiv preprint arXiv:2501.13400 (2025)","DOI":"10.29207\/resti.v10i2.6598"},{"key":"6_CR17","unstructured":"Hua, D., et al.: VABench: a comprehensive benchmark for audio-video generation. arXiv preprint arXiv:2512.09299 (2025)"},{"key":"6_CR18","unstructured":"Huang, X., Zhou, H., Yang, Q., Wen, S., Han, K.: JoVA: unified multimodal learning for joint video-audio generation. arXiv preprint arXiv:2512.13677 (2025)"},{"key":"6_CR19","doi-asserted-by":"crossref","unstructured":"Huang, Z., et\u00a0al.: VBench: comprehensive benchmark suite for video generative models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 21807\u201321818 (2024)","DOI":"10.1109\/CVPR52733.2024.02060"},{"key":"6_CR20","doi-asserted-by":"crossref","unstructured":"Iashin, V., Xie, W., Rahtu, E., Zisserman, A.: Synchformer: efficient synchronization from sparse cues. In: ICASSP 2024-2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 5325\u20135329. IEEE (2024)","DOI":"10.1109\/ICASSP48485.2024.10448489"},{"key":"6_CR21","doi-asserted-by":"crossref","unstructured":"Ke, J., Wang, Q., Wang, Y., Milanfar, P., Yang, F.: MUSIQ: multi-scale image quality transformer. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 5148\u20135157 (2021)","DOI":"10.1109\/ICCV48922.2021.00510"},{"key":"6_CR22","unstructured":"Kling: Kling (2025). https:\/\/klingai.com"},{"key":"6_CR23","doi-asserted-by":"publisher","first-page":"3367","DOI":"10.1109\/TIP.2023.3276570","volume":"32","author":"H Li","year":"2023","unstructured":"Li, H., Huang, J., Jin, P., Song, G., Wu, Q., Chen, J.: Weakly-supervised 3D spatial reasoning for text-based visual question answering. IEEE Trans. Image Process. 32, 3367\u20133382 (2023)","journal-title":"IEEE Trans. Image Process."},{"key":"6_CR24","doi-asserted-by":"crossref","unstructured":"Li, H., et\u00a0al.: OpenHumanVid: a large-scale high-quality dataset for enhancing human-centric video generation. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 7752\u20137762 (2025)","DOI":"10.1109\/CVPR52734.2025.00726"},{"issue":"9","key":"6_CR25","doi-asserted-by":"publisher","first-page":"3463","DOI":"10.1007\/s11263-024-02042-6","volume":"132","author":"H Liang","year":"2024","unstructured":"Liang, H., Zhang, W., Li, W., Yu, J., Xu, L.: InterGen: diffusion-based multi-human motion generation under complex interactions. Int. J. Comput. Vision 132(9), 3463\u20133483 (2024)","journal-title":"Int. J. Comput. Vision"},{"key":"6_CR26","unstructured":"Liu, K., et\u00a0al.: JavisDiT: joint audio-video diffusion transformer with hierarchical spatio-temporal prior synchronization. arXiv preprint arXiv:2503.23377 (2025)"},{"key":"6_CR27","unstructured":"Liu, Y., Zhu, L., Lin, L., Zhu, Y., Zhang, A., Li, Y.: Teaser: token enhanced spatial modeling for expressions reconstruction. arXiv preprint arXiv:2502.10982 (2025)"},{"key":"6_CR28","unstructured":"Low, C., Wang, W., Katyal, C.: Ovi: twin backbone cross-modal fusion for audio-video generation (2025). https:\/\/arxiv.org\/abs\/2510.01284"},{"key":"6_CR29","unstructured":"OpenAI: Sora 2: Video generation model (2025). https:\/\/openai.com\/sora"},{"key":"6_CR30","first-page":"11405","volume":"38","author":"Z Peng","year":"2026","unstructured":"Peng, Z., et al.: OmniSync: towards universal lip synchronization via diffusion transformers. Adv. Neural. Inf. Process. Syst. 38, 11405\u201311424 (2026)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"6_CR31","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning, pp. 8748\u20138763. PmLR (2021)"},{"key":"6_CR32","doi-asserted-by":"crossref","unstructured":"Reddy, C.K., Gopal, V., Cutler, R.: DNSMOS: a non-intrusive perceptual objective speech quality metric to evaluate noise suppressors. In: ICASSP 2021-2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 6493\u20136497. IEEE (2021)","DOI":"10.1109\/ICASSP39728.2021.9414878"},{"key":"6_CR33","unstructured":"Seedance, T., et\u00a0al.: Seedance 1.5 pro: a native audio-visual joint generation foundation model. arXiv preprint arXiv:2512.13507 (2025)"},{"key":"6_CR34","doi-asserted-by":"crossref","unstructured":"Soucek, T., Lokoc, J.: TransNet V2: an effective deep network architecture for fast shot transition detection. In: Proceedings of the 32nd ACM International Conference on Multimedia, pp. 11218\u201311221 (2024)","DOI":"10.1145\/3664647.3685517"},{"key":"6_CR35","doi-asserted-by":"crossref","unstructured":"Sun, M., et al.: MM-LDM: multi-modal latent diffusion model for sounding video generation. In: Proceedings of the 32nd ACM International Conference on Multimedia, pp. 10853\u201310861 (2024)","DOI":"10.1145\/3664647.3680889"},{"key":"6_CR36","unstructured":"Sun, Z., et\u00a0al.: StreamAvatar: streaming diffusion models for real-time interactive human avatars. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10887\u201310897 (2026)"},{"key":"6_CR37","doi-asserted-by":"crossref","unstructured":"Sung-Bin, K., et al.: MultiTalk: enhancing 3D talking head generation across languages with multilingual video dataset. arXiv preprint arXiv:2406.14272 (2024)","DOI":"10.21437\/Interspeech.2024-1794"},{"key":"6_CR38","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"402","DOI":"10.1007\/978-3-030-58536-5_24","volume-title":"Computer Vision \u2013 ECCV 2020","author":"Z Teed","year":"2020","unstructured":"Teed, Z., Deng, J.: RAFT: recurrent all-pairs field transforms for optical flow. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12347, pp. 402\u2013419. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58536-5_24"},{"key":"6_CR39","doi-asserted-by":"crossref","unstructured":"Tjandra, A., et al.: Meta audiobox aesthetics: unified automatic quality assessment for speech, music, and sound. arXiv preprint arXiv:2502.05139 (2025)","DOI":"10.1109\/ASRU65441.2025.11434623"},{"key":"6_CR40","unstructured":"Tschannen, M., et al.: SigLIP 2: multilingual vision-language encoders with improved semantic understanding, localization, and dense features. arXiv preprint arXiv:2502.14786 (2025)"},{"key":"6_CR41","unstructured":"Wan, T., et\u00a0al.: Wan: Open and advanced large-scale video generative models. arXiv preprint arXiv:2503.20314 (2025)"},{"key":"6_CR42","unstructured":"Wang, D., et al.: Universe-1: unified audio-video generation via stitching of experts. arXiv preprint arXiv:2509.06155 (2025)"},{"key":"6_CR43","unstructured":"Wang, J., Qiang, C., Guo, Y., Wang, Y., Zeng, X., Deng, F.: Apollo: unified multi-task audio-video joint generation. arXiv e-prints pp. arXiv\u20132601 (2026)"},{"key":"6_CR44","doi-asserted-by":"crossref","unstructured":"Wang, K., Deng, S., Shi, J., Hatzinakos, D., Tian, Y.: AV-DiT: efficient audio-visual diffusion transformer for joint audio and video generation. arXiv preprint arXiv:2406.07686 (2024)","DOI":"10.1145\/3746027.3755713"},{"key":"6_CR45","unstructured":"Wu, H., et al.: Disentangling aesthetic and technical effects for video quality assessment of user generated content. arXiv preprint arXiv:2211.04894 (2022). 2(5), 6"},{"key":"6_CR46","doi-asserted-by":"crossref","unstructured":"Wu, Y., Chen, K., Zhang, T., Hui, Y., Berg-Kirkpatrick, T., Dubnov, S.: Large-scale contrastive language-audio pretraining with feature fusion and keyword-to-caption augmentation. In: ICASSP 2023-2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp.\u00a01\u20135. IEEE (2023)","DOI":"10.1109\/ICASSP49357.2023.10095969"},{"key":"6_CR47","unstructured":"Xie, T., et\u00a0al.: PhyAVBench: a challenging audio physics-sensitivity benchmark for physically grounded text-to-audio-video generation. arXiv preprint arXiv:2512.23994 (2025)"},{"key":"6_CR48","unstructured":"Xu, J., et al.: Qwen3-omni technical report (2025). https:\/\/arxiv.org\/abs\/2509.17765"},{"issue":"4","key":"6_CR49","doi-asserted-by":"publisher","first-page":"3031","DOI":"10.1109\/TPAMI.2025.3528453","volume":"47","author":"L Yang","year":"2025","unstructured":"Yang, L., Zhao, Z., Zhao, H.: UniMatch V2: pushing the limit of semi-supervised semantic segmentation. IEEE Trans. Pattern Anal. Mach. Intell. 47(4), 3031\u20133048 (2025)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"6_CR50","unstructured":"Yang, S., et al.: InfiniteTalk: audio-driven video generation for sparse-frame video dubbing. arXiv preprint arXiv:2508.14033 (2025)"},{"key":"6_CR51","unstructured":"Yang, Z., et al.: SVBench: a benchmark with temporal multi-turn dialogues for streaming video understanding. arXiv preprint arXiv:2502.10810 (2025)"},{"key":"6_CR52","unstructured":"Zhang, G., et al.: UniAVGen: unified audio and video generation with asymmetric cross-modal interactions. arXiv preprint arXiv:2511.03334 (2025)"},{"key":"6_CR53","unstructured":"Zhang, Y., et al.: SpeakerVid-5M: a large-scale high-quality dataset for audio-visual dyadic interactive human generation. arXiv preprint arXiv:2507.09862 (2025)"},{"key":"6_CR54","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Wang, T., Zhang, X.: MOTRv2: bootstrapping end-to-end multi-object tracking by pretrained object detectors. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 22056\u201322065 (2023)","DOI":"10.1109\/CVPR52729.2023.02112"},{"key":"6_CR55","doi-asserted-by":"crossref","unstructured":"Zhang, Z., Li, L., Ding, Y., Fan, C.: Flow-guided one-shot talking face generation with a high-resolution audio-visual dataset. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3661\u20133670 (2021)","DOI":"10.1109\/CVPR46437.2021.00366"},{"key":"6_CR56","doi-asserted-by":"crossref","unstructured":"Zhou, Y.H., et\u00a0al.: MTAVG-Bench: a comprehensive benchmark for evaluating multi-talker dialogue-centric audio-video generation. arXiv preprint arXiv:2602.00607 (2026)","DOI":"10.18653\/v1\/2026.acl-long.913"},{"key":"6_CR57","doi-asserted-by":"crossref","unstructured":"Zhu, H., et al.: CelebV-HQ: a large-scale video facial attributes dataset. In: European Conference on Computer Vision, pp. 650\u2013667. Springer (2022)","DOI":"10.1007\/978-3-031-20071-7_38"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2026"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-37095-2_6","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,8]],"date-time":"2026-09-08T07:04:46Z","timestamp":1788851086000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37095-2_6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032370945","9783032370952"],"references-count":57,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37095-2_6","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"9 September 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Malm\u00f6","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Sweden","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2026","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 September 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 September 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2026","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}